Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (idempotentHint, destructiveHint, etc.), it discloses auth requirements (tickets:write), concurrency control (revision/evidence conflict), idempotency semantics (exact retries return original receipt), side effects (immutable history, omitted fields clear note/date), and a list of non-effects (does not hide/reorder queue items, reset status, notify/call providers). This is rich behavioral detail that annotations alone do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded, starting with the purpose and then moving to requirements and behavioral caveats. The final phrase 'Retained evidence discloses omitted prerequisite detail' is cryptic and adds little clarity, but overall there is no wasted content and the structure is logical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write operation with no output schema, it addresses permission, required inputs, idempotency, conflict behavior, side effects, and non-effects. It does not fully describe the receipt's contents or error handling, but it provides enough for an agent to understand the contract and invoke it safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden, and it covers six of seven parameters: note (2000 characters, optional), follow_up_date and follow_up_timezone (IANA, null for both), expected_evidence_digest, expected_review_revision (0 first), and idempotency_key (caller-stable). Only ticket_id is left to be inferred from the tool name and schema pattern, which is a minor gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource: 'Record an owner-private review of current attention evidence,' which clearly distinguishes this save-review operation from siblings such as get_ticket_attention_review or save_ticket_attention_policy. It also specifies the key parameters (note, follow-up) so the tool's scope is immediately evident.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear usage context: requires tickets:write, must supply current evidence digest, current review revision (0 first), and a caller-stable idempotency key, with explicit behavior for exact retries and conflicts. It does not, however, name alternative tools or state when not to use it, leaving the agent to infer that retrieval is done via get_ticket_attention_review.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.